rtqichen/ffjord
rtqichen/ffjord has 671 GitHub stars and 140 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-15 22:24 UTC. Last push 2020-09-22.
Measured star growth
- in 24h
- 0
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".
Developer ToolsREADME.md
OriginalFree-form Jacobian of Reversible Dynamics (FFJORD)
Code for reproducing the experiments in the paper:
Will Grathwohl*, Ricky T. Q. Chen*, Jesse Bettencourt, Ilya Sutskever, David Duvenaud. "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models." International Conference on Learning Representations (2019). [arxiv] [bibtex]
Prerequisites
Install torchdiffeq from https://github.com/rtqichen/torchdiffeq.
Usage
Different scripts are provided for different datasets. To see all options, use the -h flag.
Toy 2d:
python train_toy.py --data 8gaussians --dims 64-64-64 --layer_type concatsquash --save experiment1
Tabular datasets from MAF:
python train_tabular.py --data miniboone --nhidden 2 --hdim_factor 20 --num_blocks 1 --nonlinearity softplus --batch_size 1000 --lr 1e-3
MNIST/CIFAR10:
python train_cnf.py --data mnist --dims 64,64,64 --strides 1,1,1,1 --num_blocks 2 --layer_type concat --multiscale True --rademacher True
VAE Experiments (based on Sylvester VAE):
python train_vae_flow.py --dataset mnist --flow cnf_rank --rank 64 --dims 1024-1024 --num_blocks 2
Glow / Real NVP experiments are run using train_discrete_toy.py and train_discrete_tabular.py.
Datasets
Tabular (UCI + BSDS300)
Follow instructions from https://github.com/gpapamak/maf and place them in data/.
VAE datasets
Follow instructions from https://github.com/riannevdberg/sylvester-flows and place them in data/.
Bespoke Flows
Here's a fun script that you can use to create your own 2D flow from an image!
python train_img2d.py --img imgs/github.png --save github_flow